implement parameter min_characters_to_try for minimum characters to try to skip page entirely.

fixes #1729

Author: zdenop

src/ccmain/osdetect.cpp

@@ -36,9 +36,6 @@
 #include <algorithm>
 #include <memory>
 
-const int kMinCharactersToTry = 50;
-const int kMaxCharactersToTry = 5 * kMinCharactersToTry;
-
 const float kSizeRatioToReject = 2.0;
 const int kMinAcceptableBlobHeight = 10;
 
@@ -278,6 +275,8 @@ int os_detect_blobs(const GenericVector<int>* allowed_scripts,
                     BLOBNBOX_CLIST* blob_list, OSResults* osr,
                     tesseract::Tesseract* tess) {
   OSResults osr_;
+  int minCharactersToTry = tess->min_characters_to_try;
+  int maxCharactersToTry = 5 * minCharactersToTry;
   if (osr == nullptr)
     osr = &osr_;
 
@@ -286,13 +285,13 @@ int os_detect_blobs(const GenericVector<int>* allowed_scripts,
   ScriptDetector s(allowed_scripts, osr, tess);
 
   BLOBNBOX_C_IT filtered_it(blob_list);
-  int real_max = std::min(filtered_it.length(), kMaxCharactersToTry);
+  int real_max = std::min(filtered_it.length(), maxCharactersToTry);
   // tprintf("Total blobs found = %d\n", blobs_total);
   // tprintf("Number of blobs post-filtering = %d\n", filtered_it.length());
   // tprintf("Number of blobs to try = %d\n", real_max);
 
   // If there are too few characters, skip this page entirely.
-  if (real_max < kMinCharactersToTry / 2) {
+  if (real_max < minCharactersToTry / 2) {
     tprintf("Too few characters. Skipping this page\n");
     return 0;
   }
@@ -307,7 +306,7 @@ int os_detect_blobs(const GenericVector<int>* allowed_scripts,
   int num_blobs_evaluated = 0;
   for (int i = 0; i < real_max; ++i) {
     if (os_detect_blob(blobs[sequence.GetVal()], &o, &s, osr, tess)
-        && i > kMinCharactersToTry) {
+        && i > minCharactersToTry) {
       break;
     }
     ++num_blobs_evaluated;

src/ccmain/tesseractclass.cpp

@@ -397,6 +397,9 @@ Tesseract::Tesseract()
       INT_MEMBER(jpg_quality, 85, "Set JPEG quality level", this->params()),
       INT_MEMBER(user_defined_dpi, 0, "Specify DPI for input image",
                  this->params()),
+      INT_MEMBER(min_characters_to_try, 50,
+                 "Specify minimum characters to try to skip page entirely",
+				 this->params()),
       STRING_MEMBER(unrecognised_char, "|",
                     "Output char for unidentified blobs", this->params()),
       INT_MEMBER(suspect_level, 99, "Suspect marker level", this->params()),

src/ccmain/tesseractclass.h

@@ -1043,6 +1043,8 @@ class Tesseract : public Wordrec {
              "Create PDF with only one invisible text layer");
   INT_VAR_H(jpg_quality, 85, "Set JPEG quality level");
   INT_VAR_H(user_defined_dpi, 0, "Specify DPI for input image");
+  INT_VAR_H(min_characters_to_try, 50,
+	        "Specify minimum characters to try to skip page entirely");
   STRING_VAR_H(unrecognised_char, "|",
                "Output char for unidentified blobs");
   INT_VAR_H(suspect_level, 99, "Suspect marker level");